TY - CONF AU - Fahad Shahbaz Khan AU - Muhammad Anwer Rao AU - Joost Van de Weijer AU - Michael Felsberg AU - J.Laaksonen A2 - SCIA PY - 2015// TI - Deep semantic pyramids for human attributes and action recognition BT - Image Analysis, Proceedings of 19th Scandinavian Conference , SCIA 2015 SP - 341 EP - 353 VL - 9127 PB - Springer International Publishing KW - Action recognition KW - Human attributes KW - Semantic pyramids N2 - Describing persons and their actions is a challenging problem due to variations in pose, scale and viewpoint in real-world images. Recently, semantic pyramids approach [1] for pose normalization has shown to provide excellent results for gender and action recognition. The performance of semantic pyramids approach relies on robust image description and is therefore limited due to the use of shallow local features. In the context of object recognition [2] and object detection [3], convolutional neural networks (CNNs) or deep features have shown to improve the performance over the conventional shallow features.We propose deep semantic pyramids for human attributes and action recognition. The method works by constructing spatial pyramids based on CNNs of different part locations. These pyramids are then combined to obtain a single semantic representation. We validate our approach on the Berkeley and 27 Human Attributes datasets for attributes classification. For action recognition, we perform experiments on two challenging datasets: Willow and PASCAL VOC 2010. The proposed deep semantic pyramids provide a significant gain of 17.2%, 13.9%, 24.3% and 22.6% compared to the standard shallow semantic pyramids on Berkeley, 27 Human Attributes, Willow and PASCAL VOC 2010 datasets respectively. Our results also show that deep semantic pyramids outperform conventional CNNs based on the full bounding box of the person. Finally, we compare our approach with state-of-the-art methods and show a gain in performance compared to best methods in literature. SN - 0302-9743 SN - 978-3-319-19664-0 UR - http://www.springer.com/gp/book/9783319196640 UR - http://dx.doi.org/10.1007/978-3-319-19665-7_28 N1 - LAMP; 600.068; 600.079;ADAS ID - Fahad Shahbaz Khan2015 ER -